diff --git a/.github/workflows/nightly-test-amd-rocm720.yml b/.github/workflows/nightly-test-amd-rocm720.yml
index 89673c067..8503fba05 100644
--- a/.github/workflows/nightly-test-amd-rocm720.yml
+++ b/.github/workflows/nightly-test-amd-rocm720.yml
@@ -300,6 +300,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -339,6 +340,7 @@ jobs:
         run: |
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-2-gpu-mi35x-glm51-mxfp4 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -379,6 +381,7 @@ jobs:
         run: |
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-2-gpu-mi35x-deepseek-r1-mxfp4-tp2 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -415,6 +418,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-2-gpu-vlm --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -451,6 +455,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-perf-text-2-gpu --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
@@ -488,6 +493,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-perf-vlm-2-gpu --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
@@ -623,6 +629,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -636,6 +643,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-gpt-oss --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1005,6 +1013,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-v32 --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1016,6 +1025,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-deepseek-v32-basic --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1113,6 +1123,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-r1-mxfp4 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1124,6 +1135,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/perf/mi35x/test_deepseek_r1_mxfp4_perf_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1164,6 +1176,7 @@ jobs:
         run: |
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/accuracy/mi35x/test_deepseek_r1_mxfp4_tp4_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1175,6 +1188,7 @@ jobs:
         run: |
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/accuracy/mi35x/test_deepseek_r1_mxfp4_tp4_mtp_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1216,6 +1230,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-r1-mxfp4-kv-fp8 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1227,6 +1242,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/perf/mi35x/test_deepseek_r1_mxfp4_kv_fp8_perf_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1268,6 +1284,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-r1-mxfp4-ar-fusion --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1279,6 +1296,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/perf/mi35x/test_deepseek_r1_mxfp4_ar_fusion_perf_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1625,6 +1643,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k26 --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1672,6 +1691,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k3 --nightly --timeout-per-file 14400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1689,6 +1709,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/perf/mi35x/test_kimi_k3_perf_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1745,6 +1766,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-qwen35-fp8 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
@@ -1786,6 +1808,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-qwen35 --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1798,6 +1821,7 @@ jobs:
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-qwen35-fp8 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1837,6 +1861,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-qwen35-triton-dcp --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1895,6 +1920,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-qwen38-mxfp4 --nightly --timeout-per-file 21600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1937,6 +1963,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-glm51 --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -1948,6 +1975,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-glm51 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
@@ -1995,6 +2023,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm52-fp8 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2008,6 +2037,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-glm52-fp8 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2052,6 +2082,7 @@ jobs:
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm5-mxfp4 --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2064,6 +2095,7 @@ jobs:
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 registered/amd/perf/mi35x/test_glm5_mxfp4_perf_mi35x.py || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2151,6 +2183,7 @@ jobs:
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-4-gpu-mi35x-minimax-m3-tp4 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2165,6 +2198,7 @@ jobs:
           > github_summary.md
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-4-gpu-mi35x-minimax-m3 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
@@ -2207,6 +2241,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-minimax-m27 --nightly --timeout-per-file 3600 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
@@ -2219,6 +2254,7 @@ jobs:
         run: |
           > github_summary.md  # Clear summary file
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e SGLANG_MOE_COPY_WEIGHT_VIEWS_BEFORE_H2D=1 \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
             python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-minimax-m27 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?